Model comparison
Kimi K2.5 Instant vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.5 to 42.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 1 category and Kimi K2.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 36.6.
Side by side
| Kimi K2.5 Instant | Kimi K2.6 | |
|---|---|---|
| Provider | Moonshot AI | Moonshot AI |
| Noometry Index | 42.9 | 47.5 |
| Released | — | 2026-04-20 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.95 |
| Output $ / M tokens | — | $4 |
| Results tracked | 18 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2.5 Instant: 42.3 (#95), Kimi K2.6: 50.5 (#41)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1404 | 1509 |
| LMArena Coding | 1483 | 1488 |
| SWE-bench Verified | — | 76.7% |
| SciCode | — | 53.5% |
| WeirdML | — | 55.9% |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Not comparable
Kimi K2.5 Instant: —, Kimi K2.6: 21.8 (#128)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Kimi K2.5 Instant: 28.5 (#88), Kimi K2.6: 39.6 (#51)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1470 |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| Epoch Capabilities Index | — | 151.03 |
Math Kimi K2.6 leads
Kimi K2.5 Instant: 36.6 (#105), Kimi K2.6: 56.8 (#34)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1443 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
Kimi K2.5 Instant: 39.5 (#121), Kimi K2.6: 53.9 (#48)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Expert | 1438 | 1491 |
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| Vectara Hallucination Rate | — | 10.8% |
Multimodal Kimi K2.5 Instant leads
Kimi K2.5 Instant: 39.5 (#47), Kimi K2.6: 31.8 (#95)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1254 | 1282 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Kimi K2.5 Instant: 52.2 (#89), Kimi K2.6: 55.1 (#35)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1406 | 1446 |
| LMArena Chinese | 1450 | 1521 |
| LMArena French | 1403 | 1471 |
| LMArena German | 1413 | 1449 |
| LMArena Korean | 1378 | 1428 |
| LMArena Russian | 1404 | 1446 |
| LMArena Spanish | 1448 | 1463 |
| LMArena Japanese | — | 1442 |
Instruction Following Too close to call
Kimi K2.5 Instant: 75.5 (#61), Kimi K2.6: 76.5 (#40)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1430 | 1451 |
Long Context Kimi K2.6 leads
Kimi K2.5 Instant: 43.8 (#82), Kimi K2.6: 44.9 (#50)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1435 | 1468 |
Writing & Preference Kimi K2.6 leads
Kimi K2.5 Instant: 60.8 (#91), Kimi K2.6: 68.7 (#25)
| Benchmark | Kimi K2.5 Instant | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1420 | 1455 |
| LMArena Creative Writing | 1379 | 1434 |
| LMArena Multi-Turn | 1427 | 1453 |
| EQ-Bench Creative Writing | — | 1725 |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Kimi K2.5 Instant better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 42.9 on the Noometry Index.
Is Kimi K2.5 Instant or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 42.3 in the Noometry coding category.
How many benchmarks do Kimi K2.5 Instant and Kimi K2.6 share?
18 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Kimi K2.6 has 51.